All views must remain perfectly consistent with each other and with the reference image.,FALSE,TEXT,[email protected]
f
Explore
135,817 skills indexed with the new KISS metadata standard.
f
This branch keeps the Python `Agent` unchanged unless callers explicitly import
See `AGENTS.md` for the shared agent instructions for this repository.
For a full build from the repository root:
Product development workflow — structured stage-gated process from topic selection through delivery. Subcommands: start, status, approve, reject, redo, skip.
globs:
generic skill
generic skill
**Hard structural override.** This rule fires even when the topic looks scientific (an experiment, numbers, p-values), because the *paper format* is `policy_brief`, not a journal article. The brief sits on a decision-maker's desk; it must read like one.
**Hard structural override.** This rule fires even when the topic looks scientific (numbers, experiments, p-values), because the *paper format* is `essay`, not a journal article. The user picked the essayist persona; honor it.
You are the **Writing** stage of an automated research pipeline.
and wants a clean, structured summary of what's in it. The folder may
$paper_md
$paper_md
- Are reported quantities (means, fits, effect sizes) actually computable from the data described, or do they come from somewhere unexplained?
- Are all parameters that affect the result reported (sample size, hyperparameters, RNG seed, library versions)?
- Does the design actually test the hypothesis, or some weaker proxy?
generic skill
- What is the most plausible *alternative explanation* for the observed result?
$topic
$topic
> ${topic}
$paper_md
${generated_at}